Toward Curiosity-Driven Embodied Learning Through World Models
Abstract: Curiosity allows animals and humans to learn through interaction without explicit instruction. This thesis asks how principles of natural curiosity can be translated into embodied agents, and what kinds of world models are needed as bodies, action spaces, and environments become more complex. We study this progression in simulation, using animal behavior and neural dynamics [...]
Consistent Modeling of 4D Scenes for Perception and Generation
Abstract: A core challenge in vision is building representations that capture 3D scenes over time for both perception and generation. This thesis studies consistency across views, time, and modalities by moving from dense grid-based representations toward entity-centric scene representations that can be maintained across frames and used for interactive generation. The first part of the [...]
Data Mining and Auto-Labeling for Promptable Driving Policies
Abstract: Autonomous vehicles (AVs) are being deployed at scale today, with companies like Waymo achieving upward of 500,000 passenger rides per week. Two of the largest remaining problems in the field are 1) building a system that generalizes across the long-tail of edge cases that are represented few or no times within the training data [...]
MapForest: A Modular Field Robotics System for Forest Mapping
Abstract: Forests present compounding challenges for mobile mapping systems. Dense canopy degrades GNSS, uneven terrain demands deployment across diverse platforms, and no single sensing platform can capture the full vertical structure of a forest — from the canopy above to the understory below. Yet precise, georeferenced maps of individual trees are exactly what ecologists and [...]
Tracing Generated Content Back to Training Data
Abstract: AI-generated content is inherently derived from training data, yet it remains a mystery which specific data points large generative models rely on for a given generation. To address this, my research focuses on training data attribution—identifying the training images that are most influential in synthesizing a specific output. The ideal objective is to find [...]